Productivity & Workflow Agent Skills for Zed

Audit local Codex session health by engagement recency and safely cold-store or restore older top-level sessions without deleting history.

Orchestrates multi-session agent workflows, subagent dispatching, QA verification, and repair gates across complex development lifecycles.

Audits, streamlines, and refactors Codex and AI agent skills to eliminate redundancy and optimize prompt overhead.

Delegate a bounded analysis, implementation proposal, or independent review to a locally running Worker Gateway, then critically inspect…

Read the user's coding preferences from /memory/coding-prefs.md before making non-trivial style decisions, and append new preferences when…

Standardizes multi-agent coding workflows and orchestrates external harnesses like Claude Code, Codex, and OpenCode via the ACP protocol.

The third-wave coffee terminal — every elite roaster, every YouTube creator review, your brews, and the God cup.

Route substantive knowledge-work and evolving projects among execution, exploration, learning, research, challenge, decision, and creation…

Coding-first, generalist-capable working method that captures details bottom-up, interprets them through context, verifies them…

Dispatches a composed set of assignment envelopes to domain-expert subagents in parallel, in a single message with multiple Agent tool…

Threads the four-phase grain-to-coliseum transformation — given a dense prompt (the "grain"), autonomously surfaces parallel dimensions…

Merges the parallel returns from a dispatched coliseum into a single composed whole — alchemy, not concatenation.

Use when you want to understand what Claude contributed vs what you drove in a session.

[omh] Shell command or test-suite execution: policy overlay for terminal commands - add cwd, environment, safety, and result-evidence…

Use when reviewing, approving, or designing commercial motion — pricing models, deal review, discount approval, partnership economics…

Triage acc's open promises and close them with honest real-world verdicts via acc_act(runtime="outcome").

Batch-run simplification across changed files or a whole repository, grouped by ecosystem and dependency order.

Check context usage and compact the conversation from IPython.

Build a bounded, evidence-backed map of a repository's languages, manifests, dependencies, plugins, components, entry points, and…

Monthly CFO workflow for a company or agency — pull raw data from bank + payment processor + payroll + expense management, categorize and…

Build a Map of Content (MOC) for a company in an Obsidian vault — an ideas-first knowledge graph built from primary sources (decks…